Introduction to AI Agents

From Chatting With AI to Directing It

Course Overview

Welcome to a course designed for everyone — especially those who think tech might not be for them! This course is your next step after learning the basics of AI chat. Instead of just asking AI questions, you’ll learn to tell the difference between a one-off answer, a saved instruction set, an automation, and something that can actually make decisions and act on its own.

No coding. No technical background needed. Just a willingness to try, watch things go wrong on purpose, and try again.

What You’ll Learn

You’ll leave able to tell a Skill from an Automation from an Agent — in any AI tool, not just the one you used in class — and know exactly which one a real task needs. By the end, you’ll have designed (and quite possibly built) both a reusable Skill and a working Agent, and you’ll know the four questions to ask before you trust any agent with something real.

Course Format

1 live session · 3 hours — plus an optional 1-hour Office Hours, by sign-up, one week later.

1. The Productivity Pyramid: Tell a Skill from an Automation from an Agent — made relatable with an example everyone already knows, then sorted with examples from the group
2. Build a Skill, Then Add a Trigger: Start with what a free account can do, watch a reusable instruction set get built live, then see it turned into something that runs on its own
3. Hands-On — Build (or Role-Play) a Skill: Configure your own, and find out firsthand what happens when instructions are too vague
4. What Makes an Agent an Agent: The loop behind every AI agent — LOOK, THINK, ACT, CHECK — shown in a live demo
5. Hands-On — One Mission, Two Ways to Run It: Everyone gets the same open-ended mission — “process the incoming documents.” Then you compare what each room’s agent did
6. Guardrails & Next Steps: The four questions to ask before you trust any agent with something real

What Makes This Course Special

• Works Whether You’re on a Free or Paid AI Plan: We start with what a free account can do, then show what paid access adds. Everyone takes on the same mission in the agent exercise. Rooms are matched to what your tool can actually do, so you leave with the same understanding either way
• No Tech Background Needed: Every technical step is explained in plain language before you touch a button
• Concept First, Click Second: You’ll always know why before you’re shown how
• Real Problems Only: Every exercise uses a real document or a real task, not a toy example
• Judgment, Not Just Instructions: The agent exercise gives a deliberately open-ended mission. You see what an agent does when no one tells it each step
• Honest About Failure: We run a live agent demo and let it struggle in front of everyone — that’s exactly where the guardrails lesson lands hardest
• Honest About AI: We talk openly about what AI does well, what still needs you, and what it will get wrong

Who This Course Is For

• Anyone who’s used ChatGPT or Claude and wants to go beyond asking questions
• People on a free plan who assumed “building an AI agent” wasn’t for them yet
• Anyone who’s thought “tech isn’t really for me” — this course was made for you
• Small business owners, community organizers, creatives, students — everyone
• People who want practical judgment, not just button-clicking

If you’ve already told an AI what to write, you’re one step away from telling it what to decide.

What You’ll Leave With

• A clear, personal answer to “is this a Skill, an Automation, or an Agent?” for any task you’re staring at
• A designed Skill — reusable instructions for a real task, with a rule for what to do when it isn’t sure
• Firsthand experience of the agent loop on a real mission: what the agent looked at, what it decided, what it did, and whether anyone checked
• Your own written answers to the four trust questions, applied to a real task you plan to try this week
• (With the right access) a working Skill actually running in Claude or ChatGPT

Upon successful completion, you’ll earn a Certificate of Completion.

Part 1: The Productivity Pyramid

Most people use AI like a search engine — ask a question, get an answer, start over. This opens with an example everyone already knows — a kid doing the dishes — run three different ways, to make the difference between a Skill, an Automation, and an Agent impossible to un-see. Then a second example from the workplace: a manager heading out of office.

Key concept: A Skill answers “how do I want this done?” An Automation answers “when should it happen?” An Agent answers “what should be done here?” Agents use skills and tools, small pieces are easier to check than one big one, and you should always tell the AI what success looks like.

What you see: The same task — dishes, then an out-of-office report — run at all three levels. You then sort three scenarios together, and add examples of your own for the group to classify. A live demo follows: a Skill built, tested, and turned into a scheduled Automation.

Milestones

✓ Tell a Skill from an Automation from an Agent, using a plain-language example you could explain to anyone

✓ Watch a real Skill get built, tested, and turned into an Automation

✓ Correctly place three scenarios — and one of your own — at the right level

Part 2: Build a Skill

Time to put it into practice — configure a reusable Skill for summarizing a real document, and find out firsthand what happens when instructions are too vague. We start with the free-account experience first, including saving instructions in a Project, then show what paid access adds. If your tool can build it directly, you build it. If not, you design it and pressure-test it live with a partner through a role-play — same reasoning, same result.

Key concept: Good instructions state what to do when the AI isn’t sure — guess, do nothing, say what’s wrong, or ask. That one decision is the difference between a Skill you can trust and one that quietly makes things up.

What you build: A Skill — built live in Claude or ChatGPT, or designed and stress-tested through a live role-play — that includes an explicit rule for the moment it isn’t sure what to do.

Milestones

✓ Write instructions specific enough that someone else could follow them exactly

✓ Test your Skill against a real document — or role-play it against a deliberately awkward one

✓ Add a rule for what your Skill should do when it isn’t sure

Part 3: What Makes an Agent an Agent

Same kind of task, but now the AI has to look at the situation and decide the whole path — not just execute one fixed set of steps. This is the pattern behind every AI agent you’ll ever use. The instructor runs the demo while everyone watches the same screen, so you see the whole loop before you try it.

Key concept: The agent loop — LOOK (what’s in front of me), THINK (what does this need), ACT (use a tool), CHECK (did that work, am I done) — and knowing when to stop and ask instead of guessing.

What you see: A live, multi-step agent demo, watched turn by turn — including what happens when it gets stuck, and why that’s exactly the point.

Milestones

✓ Name the four steps of the agent loop and explain what each one is doing

✓ Correctly predict an agent’s next move mid-demo

✓ Explain why “it doesn’t know it’s stuck” is exactly why agents need guardrails

Part 4: One Mission, Two Ways to Run It

Hands-on again — and this time everyone gets the same mission: process the incoming documents. It is open-ended on purpose. Nobody tells the agent each step, so it has to use judgment: what is in front of it, what each document is, who it should go to, and when to stop and ask. Only the tools differ, and rooms are set by what your tool can actually do. A quick test at the start of the session decides where you go.

• Rooms with an agent-capable tool: Connect the sample folder. Your tool finds and opens the documents itself, makes its own routing decisions, and drafts the email it would send. Nothing is actually sent.
• Rooms without one: You play the agent loop yourselves. One person is the Agent, others play the tools (Folder, Document Reader, and a simulated email tool), and a shared Running Log is the channel between them. The AI does the real thinking: you paste what you found into a real chat and see what it decides.

Each room works from one worksheet that has the task, the prompts, and the content in one place. One person shares their screen and the others follow along.

Key concept: “Unclear → ask me” is a branch with equal status to every other option, and it is the part beginners always forget. The CHECK step is where you notice whether it asked, or whether it just acted.

What you do: Work the mission in your room, aimed at one deliberately ambiguous document, and judge it on one thing: did it ask, or did it guess? Add one instruction to fix what it got wrong. Then we come back together and compare what each room’s agent did, side by side.

Milestones

✓ Walk through LOOK → THINK → ACT → CHECK on a real mission and say what happened at each step

✓ Test it against an ambiguous document and correctly judge whether it asked or guessed

✓ Add one instruction based on something it got wrong

✓ Compare your room’s result with the other room’s and name one difference

Part 5: Guardrails, Debrief & Next Steps

Before you point any agent at something real, there are four questions worth asking every time. This closing part hands you those questions, plus a real task of your own to try them on.

Key concept: The four questions to ask before you trust any agent — what can it see, what can it do without asking, how will you know it ran, and what happens when it’s wrong.

What you leave with: Your own written answers to the four trust questions, applied to a real task you plan to try this week.

Milestones

✓ Answer the four trust questions for an agent idea of your own

✓ Leave with one real task, named out loud, to try this week

✓ Know how to reserve a spot in Office Hours if you want help building it

Bonus: Office Hours

An optional 1-hour Office Hours runs one week after the main session. Spots are limited, so sign-up is required in advance.

Come for whichever of these fits:

• Unstick Me — couldn’t find a button, hit a usage cap, your screen didn’t match
• Build an Automation — the segment we demoed but didn’t build; add a real trigger to your Skill
• Bring Your Own Task — “here’s a thing I do every week — could an agent do it?”

Free-plan participants are explicitly welcome in Office Hours — bring your design, and a facilitator in the room will help run it live.

Tools Used in This Course

AI Assistants

• Claude (claude.ai) — Projects for saving reusable instructions, scheduled tasks for running them automatically
• ChatGPT (chatgpt.com) — Projects for saving instructions, scheduled tasks for running them automatically

Whatever you already use is enough to attend. A free account is all you need to design and role-play everything in this course. A paid account (Claude Pro/Max/Team or ChatGPT Plus/Pro/Business) can unlock more of it hands-on. Which room you land in depends on what your tool can actually do, which we check with a short test at the start. Features change quickly, so please don’t rely on a plan name alone.

Digital Credentials & Certification

Certificate of Completion

Participants who attend the session, take part in both hands-on activities, and show they tried it on something real receive a Certificate of Completion for Introduction to AI Agents.

Certification Requirements

✅ Attend & Participate: Stay for the full 3-hour session with active engagement

✅ Build or Design: Complete both hands-on activities (the Skill and the Agent), whether built directly or through role-play

✅ Share Your Results: After the session, share the final instructions from your hands-on work, one thing that went wrong, and what you changed

Next Steps

After completing this course, you’ll be ready to:

• Tell a Skill from an Automation from an Agent, in any AI tool you touch
• Write instructions clear enough that an AI won’t have to guess — and know what to do when it might
• Recognize the LOOK → THINK → ACT → CHECK loop in any AI agent you use
• Ask the four trust questions before handing any agent something real
• Know exactly what to build next — and where to get help building it, in Office Hours